Cover Image

From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Yifei, Jiang, Changhao, Zhuang, Jiabao, Sun, Jiajun, Zhang, Ming, Xi, Zhiheng, Li, Hui, Dou, Shihan, Wang, Yuran, Zhang, Yunke, Ji, Tao, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challenges
by: Li, Hui, et al.
Published: (2025)

What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
by: Fan, Xiaoran, et al.
Published: (2025)

MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models
by: Huang, Wen-Chin, et al.
Published: (2024)

Universal Preference-Score-based Pairwise Speech Quality Assessment
by: Shi, Yu-Fei, et al.
Published: (2025)

HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment
by: Ren, Wenze, et al.
Published: (2025)

AttentiveMOS: A Lightweight Attention-Only Model for Speech Quality Prediction
by: Kibria, Imran E, et al.
Published: (2024)

The VoiceMOS Challenge 2024: Beyond Speech Quality Prediction
by: Huang, Wen-Chin, et al.
Published: (2024)

MOS-Bias: From Hidden Gender Bias to Gender-Aware Speech Quality Assessment
by: Ren, Wenze, et al.
Published: (2026)

CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents
by: Huang, Wen-Chin, et al.
Published: (2026)

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
by: Zhang, Hanlin, et al.
Published: (2026)

Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024
by: Kunešová, Marie, et al.
Published: (2025)

SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment
by: Tang, Yuxun, et al.
Published: (2025)

Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards
by: Ren, Yong, et al.
Published: (2026)

APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech
by: Lian, Zhicheng, et al.
Published: (2025)

FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis
by: Guo, Yinlin, et al.
Published: (2024)

SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
by: Li, Ruiqi, et al.
Published: (2026)

TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking
by: Zhou, Junzuo, et al.
Published: (2024)

SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment
by: Cao, Fengyuan, et al.
Published: (2026)

MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction
by: Zhou, Wangjin, et al.
Published: (2024)

Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms
by: Zhang, Chu Yuan, et al.
Published: (2023)

Towards Robust Audio Deepfake Detection: A Evolving Benchmark for Continual Learning
by: Zhang, Xiaohui, et al.
Published: (2024)

VoxEffects: A Speech-Oriented Audio Effects Dataset and Benchmark
by: Zhang, Zhe, et al.
Published: (2026)

Fewer-token Neural Speech Codec with Time-invariant Codes
by: Ren, Yong, et al.
Published: (2023)

WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
by: Zhou, Junzuo, et al.
Published: (2024)

SingMOS: An extensive Open-Source Singing Voice Dataset for MOS Prediction
by: Tang, Yuxun, et al.
Published: (2024)

SpeechAlign: Aligning Speech Generation to Human Preferences
by: Zhang, Dong, et al.
Published: (2024)

Speech Quality-Based Localization of Low-Quality Speech and Text-to-Speech Synthesis Artefacts
by: Kuhlmann, Michael, et al.
Published: (2026)

Unifying Listener Scoring Scales: Comparison Learning Framework for Speech Quality Assessment and Continuous Speech Emotion Recognition
by: Hu, Cheng-Hung, et al.
Published: (2025)

Learning-based A Posteriori Speech Presence Probability Estimation and Applications
by: Tao, Shuai, et al.
Published: (2025)

The AudioMOS Challenge 2025
by: Huang, Wen-Chin, et al.
Published: (2025)

Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study
by: Chen, Peikun, et al.
Published: (2024)

Learning Time-Graph Frequency Representation for Monaural Speech Enhancement
by: Wang, Tingting, et al.
Published: (2025)

S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models
by: Fang, Yuanbo, et al.
Published: (2025)

ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting
by: Zhang, Yu, et al.
Published: (2025)

Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting
by: Kondo, Yuto, et al.
Published: (2025)

ReFESS-QI: Reference-Free Evaluation For Speech Separation With Joint Quality And Intelligibility Scoring
by: Frummer, Ari, et al.
Published: (2025)

The T12 System for AudioMOS Challenge 2025: Audio Aesthetics Score Prediction System Using KAN- and VERSA-based Models
by: Yamamoto, Katsuhiko, et al.
Published: (2025)

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
by: Lu, Jingyu, et al.
Published: (2026)

Direct Preference Optimization for Speech Autoregressive Diffusion Models
by: Liu, Zhijun, et al.
Published: (2025)

The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
by: Baba, Kaito, et al.
Published: (2024)